├── notes.md ├── .gitignore └── README.md /notes.md: -------------------------------------------------------------------------------- 1 | "First, implicit feedback contains weak signals about a user’s preference: the selected items in the past give a weak indicator of what a user likes. Implicit feedback usually does not contain negative interactions, instead weak negatives are derived from all the remaining items, i.e., the items that a user has not interacted with." 2 | 3 | "Item recommenders 4 | are usually trained either (a) using sampling or (b) specialized algorithms taking 5 | into account model and loss structure." 6 | 7 | 8 | "For a good user experience there are other considerations besides high scores when selecting items. For example, diversity of results and slate optimization are important factors [28, 11]. A naive implementation just returns the top scoring items. While each item that is shown to a user might be individually 9 | a good choice, the combination of items might be suboptimal. For example, 10 | showing item i might make item j less attractive if i and j are very close or 11 | even interchangeable. Instead, it might be better to choose an item l that 12 | complements i better – even if l has a lower score than j. Diversification of result 13 | sets is an example to avoid some of these effects" 14 | 15 | 16 | "In netflix data set naybe user has a preference by popular movie against super personalized recommendations, it has a opposite behavior on music dataset where user prefer much perzonalied recommendations" 17 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Awesome-recsys 2 | "Recommender systems are often characterized as tools that help users in their decision-making process" 3 | 1. [Blogs post](#blogs-post) 4 | 2. [Videos](#Videos) 5 | 3. [Online Courses](#Online-Courses) 6 | 4. [Books](#books) 7 | 5. [Code](#code) 8 | 6. [Datasets](#datasets) 9 | 7. [Papers](#papers) 10 | 8. [Other Awesone list](#other-awesone-list) 11 | 12 | 13 | 14 | ## Blogs post 15 | 16 | * https://medium.datadriveninvestor.com/how-to-build-a-recommendation-system-for-purchase-data-step-by-step-d6d7a78800b6 17 | * https://www.kaggle.com/c/santander-product-recommendation 18 | * https://www.kaggle.com/retailrocket/ecommerce-dataset/home 19 | * https://www.kaggle.com/dschettler8845/recsys-2020-ecommerce-dataset/tasks?taskId=3124 20 | * https://www.kaggle.com/sohamohajeri/recommendation-system-for-electronic-dataset 21 | * https://towardsdatascience.com/extreme-deep-factorization-machine-xdeepfm-1ba180a6de78 22 | * https://medium.com/building-creative-market/word2vec-inspired-recommendations-in-production-f2c6a6b5b0bf 23 | * https://medium.com/shoprunner/fetching-better-beer-recommendations-with-collie-part-1-18c73ab30fbd 24 | * https://towardsdatascience.com/deep-dive-into-netflixs-recommender-system-341806ae3b48 25 | * [Applying word2vec to Recommenders and Advertising `Jun 2018`](http://mccormickml.com/2018/06/15/applying-word2vec-to-recommenders-and-advertising/) 26 | * [Instacart Market Basket Analysis. Winner’s Interview: 2nd place, Kazuki Onodera](https://medium.com/kaggle-blog/instacart-market-basket-analysis-feda2700cded) 27 | * [Back From RecSys 2021](https://medium.com/@santiago_19815/back-from-recsys-2021-288c7fa40422) 28 | * [Building a Multi-Stage Recommendation System (Part 1.1) `Dailymotion` `two tower`](https://medium.com/mlearning-ai/building-a-multi-stage-recommendation-system-part-1-1-95961ccf3dd8) 29 | * [Building a multi-stage recommendation system (part 1.2) `Dailymotion` `two tower`](https://medium.com/mlearning-ai/building-a-multi-stage-recommendation-system-part-1-2-ce006f0825d1) 30 | * [Beyond Recommendation Engines](https://medium.com/hellofresh-dev/beyond-recommendation-engines-a7ab13c14fa0) 31 | * [Pinterest Home Feed Unified Lightweight Scoring: A Two-tower Approach](https://medium.com/pinterest-engineering/pinterest-home-feed-unified-lightweight-scoring-a-two-tower-approach-b3143ac70b55) 32 | * [H&M Personalized Fashion Recommendations](https://www.kaggle.com/competitions/h-and-m-personalized-fashion-recommendations/discussion/324070) 33 | * https://medium.com/@sanchitgarg_78552/recommendations-for-h-m-ecommerce-ai-driven-retail-b0edde6746e6 34 | * [Context-Aware Recommender Systems introduction: take SQN as an example](https://medium.com/@b08902022/context-aware-recommender-systems-introduction-take-sqn-as-an-example-453b6c66172) 35 | * [Paper Review Monolith: Towards Better Recommendation Systems `TikTok`](https://pub.towardsai.net/paper-review-monolith-towards-better-recommendation-systems-b58702be416a) 36 | * [Real-time customer behavior recommendations via session-based approach](https://becominghuman.ai/real-time-customer-behavior-recommendations-via-session-based-approach-50d9faf36877) 37 | * [Personalized Fishbowl Recommendations with Learned Embeddings: Part 1 `Glassdoor`](https://medium.com/glassdoor-engineering/personalized-fishbowl-recommendations-with-learned-embeddings-part-1-6031abe84661) 38 | * [Knowledge Graph Attention Network for Recommendation](https://medium.com/@shivanshsethi8821/knowledge-graph-attention-network-for-recommendation-4be007989076) 39 | * [Training Larger and Faster Recommender Systems with PyTorch Sparse Embeddings](https://medium.com/nvidia-merlin/training-larger-and-faster-recommender-systems-with-pytorch-sparse-embeddings-53348a2cde3f) 40 | * [End-to-End Recommender Systems with Merlin: Part 3](https://medium.com/@aryan.gupta18/end-to-end-recommender-systems-with-merlin-part-3-d0d3d7e30c43) 41 | * [Recommendation Systems with Deep Learning](https://medium.com/google-cloud/recommendation-systems-with-deep-learning-69e5c1772571) 42 | * [Pinterest Home Feed Unified Lightweight Scoring: A Two-tower Approach](https://medium.com/pinterest-engineering/pinterest-home-feed-unified-lightweight-scoring-a-two-tower-approach-b3143ac70b55) 43 | * [Modern Recommender Systems](https://towardsdatascience.com/modern-recommender-systems-a0c727609aa8) 44 | * [Semantic Label Representation with an Application on Multimodal Product Categorization](https://medium.com/walmartglobaltech/semantic-label-representation-with-an-application-on-multimodal-product-categorization-63d668b943b7) 45 | * [Looking to build a recommendation system on Google Cloud? Leverage the following guidelines to identify the right solution for you (Part I)](https://cloud.google.com/blog/topics/developers-practitioners/looking-build-recommendation-system-google-cloud-leverage-following-guidelines-identify-right-solution-you-part-i) 46 | * [Google: About recommendation models](https://cloud.google.com/retail/docs/models#si) 47 | * ->[Learning product similarity in e-commerce using a supervised approach](https://towardsdatascience.com/learning-product-similarity-in-e-commerce-using-a-supervised-approach-525d734afd99) 48 | * [Recommender System — Bayesian personalized ranking from implicit feedback](https://towardsdatascience.com/recommender-system-bayesian-personalized-ranking-from-implicit-feedback-78684bfcddf6) 49 | * [10 Recommendation Techniques: Summary & Comparison](https://medium.com/@jchen001/10-recommendation-techniques-introduction-comparison-7ba4a3a2c940) 50 | 51 | 52 | ### RecSys series 53 | #### by James Le 54 | * [Part 1: An Executive Guide to Building Recommendation System](https://towardsdatascience.com/recommendation-system-series-part-1-an-executive-guide-to-building-recommendation-system-608f83e2630a) 55 | * [Part 2: The 10 Categories of Deep Recommendation Systems That…](https://towardsdatascience.com/recommendation-system-series-part-2-the-10-categories-of-deep-recommendation-systems-that-189d60287b58) 56 | * [Part 3: The 6 Research Directions of Deep Recommendation Systems That…](https://towardsdatascience.com/recommendation-system-series-part-3-the-6-research-directions-of-deep-recommendation-systems-that-3a328d264fb7) 57 | * [Part 4: The 7 Variants of MF For Collaborative Filtering](https://towardsdatascience.com/recsys-series-part-4-the-7-variants-of-matrix-factorization-for-collaborative-filtering-368754e4fab5) 58 | * [Part 5: The 5 Variants of MLP for Collaborative Filtering](https://towardsdatascience.com/recsys-series-part-5-neural-matrix-factorization-for-collaborative-filtering-a0aebfe15883) 59 | * [Part 6: The 6 Variants of Autoencoders for Collaborative Filtering](https://towardsdatascience.com/recommendation-system-series-part-6-the-6-variants-of-autoencoders-for-collaborative-filtering-bd7b9eae2ec7) 60 | * [Part 7: The 3 Variants of Boltzmann Machines for Collaborative Filtering](https://towardsdatascience.com/recsys-series-part-7-the-3-variants-of-boltzmann-machines-for-collaborative-filtering-4c002af258f9) 61 | 62 | #### by Eugen Yan 63 | * https://eugeneyan.com/tag/recsys/ 64 | * [RecSys 2020: Takeaways and Notable Papers](https://eugeneyan.com/writing/recsys2020/#towards-more-robust-offline-evaluation-and-study-reproducibility) 65 | * [RecSys 2021: Papers and Talks to Chew on](https://eugeneyan.com/writing/recsys2021/) 66 | * [RecSys 2022: Recap, Favorite Papers, and Lessons](https://eugeneyan.com/writing/recsys2022/) 67 | * [Patterns for Personalization](https://eugeneyan.com/writing/patterns-for-personalization/) 68 | 69 | #### by Wei Wei 70 | * **Building recommendation systems with TensorFlow** - https://www.youtube.com/watch?v=RWlLaWMD30M&list=PLQY2H8rRoyvy2MiyUBz5RWZr5MPFkV3qz 71 | 72 | 73 | ### Algorithms 74 | #### Deep learning for recsys 75 | * [Recommender Systems using Deep Learning in PyTorch from scratch](https://towardsdatascience.com/recommender-systems-using-deep-learning-in-pytorch-from-scratch-f661b8f391d7) 76 | * [Modern Recommender Systems. - A Deep Dive into the AI algorithms [Jun 2021]](https://towardsdatascience.com/modern-recommender-systems-a0c727609aa8) 77 | * [pytorch-for-recommenders-101](https://blog.fastforwardlabs.com/2018/04/10/pytorch-for-recommenders-101.html) `Apr 2018` 78 | * [Deep Learning Recommendation Models (DLRM) : A Deep Dive ](https://medium.com/swlh/deep-learning-recommendation-models-dlrm-a-deep-dive-f38a95f47c2c) `Oct 2020` 79 | * [deep-learning-recommendation-models-dlrm-deep-dive ](https://www.kdnuggets.com/2021/04/deep-learning-recommendation-models-dlrm-deep-dive.html) `Apr 2021` 80 | 81 | #### Probabilistic approach 82 | * https://www.cs.toronto.edu/~amnih/papers/bpmf.pdf 83 | * https://towardsdatascience.com/probabilistic-matrix-factorization-b7852244a321 84 | * https://docs.pymc.io/notebooks/probabilistic_matrix_factorization.html 85 | 86 | #### Implicit RecSys 87 | * [Building (and Evaluating) a Recommender System for Implicit Feedback](https://medium.com/@judaikawa/building-and-evaluating-a-recommender-system-for-implicit-feedback-59495d2077d4) 88 | * -> [Factorization Machines for Item Recommendation with Implicit Feedback Data](https://towardsdatascience.com/factorization-machines-for-item-recommendation-with-implicit-feedback-data-5655a7c749db) 89 | 90 | #### Learn to Rank 91 | * [Pointwise vs. Pairwise vs. Listwise Learning to Rank](https://medium.com/@nikhilbd/pointwise-vs-pairwise-vs-listwise-learning-to-rank-80a8fe8fadfd) 92 | * [Advances in TF-Ranking](https://ai.googleblog.com/2021/07/advances-in-tf-ranking.html) 93 | 94 | #### Graph 95 | * [Network models for recommender systems](https://medium.com/dunnhumby-data-science-engineering/network-models-for-recommender-systems-7f0d6d210ccf) 96 | 97 | #### Reinforcement Learning 98 | * -> [RL in RecSys, an overview](https://scitator.medium.com/rl-in-recsys-an-overview-e02815019a8f) 99 | * [Build a reinforcement learning recommendation application using Vertex AI](https://cloud.google.com/blog/topics/developers-practitioners/build-reinforcement-learning-recommendation-application-using-vertex-ai) 100 | * [Building Self learning Recommendation System using Reinforcement Learning : Part I](https://bayesianquest.com/2022/01/03/building-self-learning-recommendation-system-using-reinforcement-learning-part-i/) 101 | * [Reinforcement learning in Recommender systems, with Kim Folk](https://www.youtube.com/watch?v=1a5YSU2ho_I) 102 | 103 | 104 | #### Transformers 105 | * [https://medium.com/genifyai/genify-transformer-model-recommender-system-6cd0c8414527](https://medium.com/genifyai/genify-transformer-model-recommender-system-6cd0c8414527) 106 | 107 | #### Autoencoders 108 | * [How Variational Autoencoders make classical recommender systems obsolete.](https://medium.com/snipfeed/how-variational-autoencoders-make-classical-recommender-systems-obsolete-4df8bae51546) 109 | * [Implementation of deep generative models for recommender systems in Tensorflow🔮 Implementation of VAEs and GANs](https://medium.com/snipfeed/how-to-implement-deep-generative-models-for-recommender-systems-29110be8971f) 110 | 111 | #### Hands-on 112 | * https://taufik-azri.medium.com/recommendation-system-for-retail-customer-3f0f80b84221 113 | * https://colab.research.google.com/github/google/eng-edu/blob/main/ml/recommendation-systems/recommendation-systems.ipynb 114 | 115 | 116 | ### Evaluation metrics for RecSys 117 | * [Evaluation Metrics for Recommender Systems](https://towardsdatascience.com/evaluation-metrics-for-recommender-systems-df56c6611093) 118 | * [MAP@k](http://sdsawtelle.github.io/blog/output/mean-average-precision-MAP-for-recommender-systems.html) 119 | * -> [KDD 2021 Mixed Method Development of Evaluation Metrics](https://kdd2021-mixedmethods.github.io/) 120 | * -> [KDD 2020 Tutorial on Online User Engagement](https://onlineuserengagement.github.io/) 121 | * [RecSys 2020 Session P2A: Evaluating and Explaining Recommendations](https://www.youtube.com/watch?v=90xFB3qZxuI) 122 | 123 | 124 | ### RecSys in tech companies 125 | #### OLX 126 | * https://tech.olx.com/item2vec-neural-item-embeddings-to-enhance-recommendations-1fd948a6f293 127 | #### DoorDash 128 | * [**Simple logistic regression model for recommendation**](https://doordash.news/2017/07/07/powering-search-recommendations-at-doordash/) 129 | * [**Store2Vec**](https://doordash.engineering/2018/04/02/personalized-store-feed-with-vector-embeddings/) 130 | * [**Using Triplet Loss and Siamese Neural Networks to Train Catalog Item Embeddings**](https://doordash.engineering/2021/09/08/using-twin-neural-networks-to-train-catalog-item-embeddings/) 131 | * [Things Not Strings](https://doordash.engineering/2020/12/15/understanding-search-intent-with-better-recall/) 132 | * [**Personalized Cuisine Filter**](https://doordash.engineering/2020/01/27/personalized-cuisine-filter/) 133 | 134 | #### Airbnb 135 | * [**Listing Embeddings in Search Ranking**](https://medium.com/airbnb-engineering/listing-embeddings-for-similar-listing-recommendations-and-real-time-personalization-in-search-601172f7603e) 136 | * [Improving Deep Learning for Ranking Stays at Airbnb](https://medium.com/airbnb-engineering/improving-deep-learning-for-ranking-stays-at-airbnb-959097638bde) 137 | * [Applying Deep Learning To Airbnb Search](https://arxiv.org/pdf/1810.09591.pdf) 138 | * [Improving Deep Learning For Airbnb Search](https://arxiv.org/pdf/2002.05515.pdf) 139 | * [Managing Diversity in Airbnb Search](https://arxiv.org/pdf/2004.02621.pdf) 140 | * [How we use automl multi task learning and multi tower models for pinterest ads](https://medium.com/pinterest-engineering/how-we-use-automl-multi-task-learning-and-multi-tower-models-for-pinterest-ads-db966c3dc99e) 141 | * [Pinnersage multi modal user embedding framework for recommendations at pinterest](https://medium.com/pinterest-engineering/pinnersage-multi-modal-user-embedding-framework-for-recommendations-at-pinterest-bfd116b49475) 142 | * [Driving shopping upsells from pinterest search](https://medium.com/pinterest-engineering/driving-shopping-upsells-from-pinterest-search-d06329255402) 143 | * [Using pid controllers to diversify content types on home feed](https://medium.com/pinterest-engineering/using-pid-controllers-to-diversify-content-types-on-home-feed-1c7195c89218) 144 | * [Searchsage learning search query representations at pinterest](https://medium.com/pinterest-engineering/searchsage-learning-search-query-representations-at-pinterest-654f2bb887fc) 145 | * [Pinterest home feed unified lightweight scoring a two tower approach](https://medium.com/pinterest-engineering/pinterest-home-feed-unified-lightweight-scoring-a-two-tower-approach-b3143ac70b55) 146 | * [The machine learning behind delivering relevant ads](https://medium.com/pinterest-engineering/the-machine-learning-behind-delivering-relevant-ads-8987fc5ba1c0) 147 | * [Advertiser recommendation systems at pinterest](https://medium.com/pinterest-engineering/advertiser-recommendation-systems-at-pinterest-ccb255fbde20) 148 | * [Detecting image similarity in near real time using apache flink](https://medium.com/pinterest-engineering/detecting-image-similarity-in-near-real-time-using-apache-flink-723ce072b7d2) 149 | 150 | #### Pinteres 151 | * [**Improving the Quality of Recommended Pins with Lightweight Ranking** (2020)](https://medium.com/pinterest-engineering/improving-the-quality-of-recommended-pins-with-lightweight-ranking-8ff5477b20e3) 152 | * [**Advertiser Recommendation Systems at Pinterest**](https://medium.com/pinterest-engineering/advertiser-recommendation-systems-at-pinterest-ccb255fbde20) 153 | #### Spotify 154 | * -> [How Spotify Recommends Your New Favorite Artist (2019)](https://towardsdatascience.com/how-spotify-recommends-your-new-favorite-artist-8c1850512af0) 155 | * [How does Spotify's recommendation system work?](https://www.univ.ai/post/spotify-recommendations) 156 | 157 | #### Uber 158 | * [Food Discovery with Uber Eats: Recommending for the Marketplace (2018)](https://eng.uber.com/uber-eats-recommending-marketplace/) 159 | 160 | #### Facebook 161 | * [Powered by AI: Instagram’s Explore recommender system](https://ai.facebook.com/blog/powered-by-ai-instagrams-explore-recommender-system/) 162 | 163 | #### fennel 164 | * [Real World Recommendation System - Part 1](https://blog.fennel.ai/p/real-world-recommendation-system?s=r) 165 | 166 | #### eBay 167 | * [Multi-Objective Ranking for Promoted Auction Items `eBay`](https://medium.com/@ebaytechblog/multi-objective-ranking-for-promoted-auction-items-293bf204574f) 168 | 169 | #### Expedia 170 | * [How to Optimise Rankings with Cascade Bandits](ttps://medium.com/expedia-group-tech/how-to-optimise-rankings-with-cascade-bandits-5d92dfa0f16b) 171 | 172 | #### Booking 173 | * [Personalization in Practice - Booking workshop](https://booking.ai/personalization-in-practice-2bb4bc680eb3) 174 | 175 | #### NVIDIA 176 | * https://developer.nvidia.com/blog/how-to-build-a-winning-recommendation-system-part-1/ 177 | * https://developer.nvidia.com/blog/how-to-build-a-winning-recommendation-system-part-2-deep-learning-for-recommender-systems/ 178 | * [Nvidea Merlin](https://rapids.ai/merlin.html) 179 | * [Nvidia Merlin documentation ](https://developer.nvidia.com/nvidia-merlin) 180 | * [NVTabular doc](https://nvidia-merlin.github.io/NVTabular/main/index.html) 181 | * [NVIDIA Merlin vs TensorFlow Recommenders: A comparison of these recommendation frameworks](https://analyticsindiamag.com/nvidia-merlin-vs-tensorflow-recommenders-a-comparison-of-these-recommendation-frameworks/) 182 | * [Training Deep Learning Based Recommender Systems 9x Faster with TensorFlow](https://medium.com/nvidia-merlin/training-deep-learning-based-recommender-systems-9x-faster-with-tensorflow-cc5a2572ea49) 183 | * [GTC 2020: NVTabular: GPU Accelerated ETL for Recommender Systems](https://resources.nvidia.com/c/GTC2020-s21651?x=yBY2dT&lx=jsVNdg) 184 | * [](https://docs.nvidia.com/deeplearning/dali/user-guide/docs/#) 185 | * [Overcoming Data Preprocessing Bottlenecks with TensorFlow Data Service, NVIDIA DALI, and Other Methods](https://towardsdatascience.com/overcoming-data-preprocessing-bottlenecks-with-tensorflow-data-service-nvidia-dali-and-other-d6321917f851) 186 | * [Accelerating ETL for Recommender Systems on NVIDIA GPUs with NVTabular](https://developer.nvidia.com/blog/accelerating-etl-for-recsys-on-gpus-with-nvtabular/) 187 | * [Scalable Recommender Systems with NVTabular- A Fast Tabular Data Loading and Transformation Library](https://medium.com/rapids-ai/gpu-recommender-systems-with-nvtabular-eee056c37ea0) 188 | * Summit 2021: 189 | * https://developer.nvidia.com/blog/using-neural-networks-for-your-recommender-system/?ncid=progr-559712#cid=dl19_progr_en-us 190 | * https://developer.nvidia.com/blog/nvidia-earns-1st-place-in-recsys-challenge-2021/?ncid=progr-290013#cid=dl19_progr_en-us 191 | * https://www.nvidia.com/en-us/training/instructor-led-workshops/intelligent-recommender-systems/ 192 | * https://developer.nvidia.com/nvidia-merlin?ncid=progr-101132#cid=dl19_progr_en-us 193 | * https://medium.com/nvidia-merlin/winning-the-recsys2021-challenge-by-a-diverse-set-of-xgboost-and-neural-network-models-4c5422a642d8 194 | * https://on24static.akamaized.net/event/32/96/53/0/rt/1/documents/resourceList1627506368727/nvidiarecsyssummit1627506366215.pdf 195 | * https://on24static.akamaized.net/event/32/96/53/0/rt/1/documents/resourceList1627506400731/deeplearningrecsysday21627506398728.pdf 196 | * https://on24static.akamaized.net/event/32/96/53/0/rt/1/documents/resourceList1627506417526/tensorflowrecommendersnvidia11627506415818.pdf 197 | * [Recommender Systems Summit 2022](https://www.youtube.com/watch?v=9rouLchcC0k&t=97s) 198 | 199 | * [**Recommender Systems, Not Just Recommender Models (four stages)**](https://medium.com/nvidia-merlin/recommender-systems-not-just-recommender-models-485c161c755e) 200 | 201 | #### Google 202 | * [Matrix factorization with BQML](https://medium.com/google-cloud/how-to-build-a-recommendation-system-on-e-commerce-data-using-bigquery-ml-df9af2b8c110) 203 | * [**Find anything blazingly fast with Google's vector search technology**](https://cloud.google.com/blog/topics/developers-practitioners/find-anything-blazingly-fast-googles-vector-search-technology) 204 | * [Looking to build a recommendation system on Google Cloud? Leverage the following guidelines to identify the right solution for you (Part I)](https://cloud.google.com/blog/topics/developers-practitioners/looking-build-recommendation-system-google-cloud-leverage-following-guidelines-identify-right-solution-you-part-i) 205 | 206 | #### AWS 207 | * [**What’s new in recommender systems**](https://aws.amazon.com/blogs/media/whats-new-in-recommender-systems/) 208 | 209 | 210 | 211 | ## Videos 212 | * -> [Personalizing Explainable Recommendations with Multi-objective Contextual Bandits (Spotify)](https://www.youtube.com/watch?v=KoMKgNeUX4k) 213 | * -> [MORS: Workshop on Multi-Objective Recommender Systems](https://www.youtube.com/watch?v=CeNfq6_VX2s) 214 | * [**Shared Neural Item Representations for Completely Cold Start Problem**](https://www.youtube.com/watch?v=oLsdP47K8qc) 215 | * [Maciej Kula | Neural Networks for Recommender Systems](https://www.youtube.com/watch?v=ZkBQ6YA9E40) 216 | * [Building Production Recommender Systems - Maciej Kula - WEB2DAY 2017](https://www.youtube.com/watch?v=CLNFmm6Lj_I) 217 | * [ Building AI-based Recommendation Systems, a value-based approach - Xiquan Cui ](https://www.youtube.com/watch?v=Ax_TNqJrR5s&list=PLRJL9rjwb40l0FFb4loYysgqob_GYImp-) 218 | * [ Introduction to the OTTO competition on Kaggle (RecSys) ](https://www.youtube.com/watch?v=gtPEX_eRAVo) 219 | * [ Rishabh Mehrotra: Recommendations in a Marketplace (part 1) ](https://www.youtube.com/watch?v=sx9lKCCeWoc) 220 | * [ Rishabh Mehrotra: Recommendations in a Marketplace (part 2) ](https://www.youtube.com/watch?v=3gPYN61ZGAI) 221 | 222 | 223 | 224 | ## Online Courses 225 | * Recommender Systems and Deep Learning in Python - https://www.udemy.com/course/recommender-systems/ 226 | * Building Recommender Systems with Machine Learning and AI - https://www.udemy.com/course/building-recommender-systems-with-machine-learning-and-ai/ 227 | * Google course for RecSys - https://developers.google.com/machine-learning/recommendation 228 | * ACM Summer School on Recommender Systems 2017 - http://pro.unibz.it/projects/schoolrecsys17/program.html 229 | * Recommender Systems Specialization (University of Minnesota) - https://www.coursera.org/specializations/recommender-systems 230 | * Build an ML Recommender System - https://www.manning.com/liveproject/build-an-ML-recommender-system 231 | * Workshops 232 | * Workshop on context-awere recommendation system - https://cars-workshop.com/cars-2021 233 | * [Machine Learning Recommender System With Python 2022 `Data Academy`](https://www.youtube.com/playlist?list=PLsugXK9b1w1nlDH0rbxIufJLeC3MsbRaa) 234 | * [Personalized Recommendations at Scale](https://corise.com/course/personalized-recommendation-at-scale) 235 | 236 | 237 | 238 | 239 | ## Books 240 | * [Practical Recommender Systems](https://www.manning.com/books/practical-recommender-systems) 241 | * [Recommender Systems Handbook 2rd ed. 2011 Edition](https://raw.githubusercontent.com/melissakou/Recommender-Systems-Handbook/main/%5BBook%5D%20Recommender%20Systems%20Handbook.pdf) 242 | * [Recommender Systems Handbook 3rd ed. 2022 Edition](https://www.amazon.com/Recommender-Systems-Handbook-Francesco-Ricci/dp/1071621963) 243 | * [Recommender Systems Textbook 1er ed 2016 Edition](https://www.amazon.com/Recommender-Systems-Textbook-Charu-Aggarwal-dp-3319296574/dp/3319296574/ref=mt_other?_encoding=UTF8&me=&qid=) 244 | * [Recommendation Engines](https://www.amazon.com/Recommendation-Engines-Press-Essential-Knowledge/dp/0262539071) 245 | * [Recommender Systems: An Introduction](https://www.amazon.com/Recommender-Systems-Introduction-Dietmar-Jannach/dp/0521493366) 246 | * [Personalized Machine Learning](https://cseweb.ucsd.edu/~jmcauley/pml/pml_book.pdf) 247 | 248 | 249 | ## Code 250 | ### Implementations 251 | * https://github.com/lyst/lightfm 252 | * https://github.com/benfred/implicit 253 | * https://github.com/maciejkula/spotlight 254 | * https://github.com/shenweichen/DeepCTR 255 | * https://github.com/etlundquist/rankfm 256 | * https://github.com/tensorflow/recommenders [quick start](https://www.tensorflow.org/recommenders/examples/quickstart) 257 | * https://github.com/jfkirk/tensorrec 258 | * https://github.com/tensorflow/ranking/ 259 | * https://github.com/RUCAIBox/RecBole 260 | * https://github.com/ShopRunner/collie_recs/ 261 | * https://github.com/metarank/metarank 262 | * https://github.com/linkedin/detext 263 | * https://github.com/PreferredAI/cornac/ 264 | 265 | ### competition and hands-on 266 | * https://github.com/hojinYang/spotify_recSys_challenge_2018 267 | * -> [tfrs-movierec-serving](https://github.com/hojinYang/tfrs-movierec-serving) 268 | * [recsys_autoencoders](https://github.com/marlesson/recsys_autoencoders) 269 | * [Build a recommendation system with TensorFlow and Keras `two tower`](https://github.com/xei/recommender-system-tutorial/blob/main/recommender_system_tutorial.ipynb) 270 | * [WSDM Cup on Cross-Market Recommendation Competition](https://xmrec.github.io/wsdmcup/) 271 | 272 | 273 | ## Datasets 274 | * https://www.kaggle.com/retailrocket/ecommerce-dataset 275 | * https://gist.github.com/entaroadun/1653794 276 | * https://github.com/RUCAIBox/RecSysDatasets 277 | * 30music / impresions / tv audience - https://recsys.deib.polimi.it/datasets/ 278 | * http://archive.ics.uci.edu/ml/datasets/KASANDR 279 | * yambda https://huggingface.co/datasets/yandex/yambda 280 | 281 | 282 | 283 | ## Papers 284 | [Connected papers](https://www.connectedpapers.com/) 285 | 286 | [ACM](https://dl.acm.org/topic/conference-collections/recsys?) 287 | 288 | * **OpenTable recommendations (2015)** - https://www.slideshare.net/BuhwanJeong/deep-learning-c-43529709 289 | * 2001 290 | * [Item-Based Collaborative Filtering Recommendation Algorithms `GroupLens`](https://dl.acm.org/doi/pdf/10.1145/371920.372071) 291 | * 2004 292 | * [Item-based top-N recommendation algorithms](https://dl.acm.org/doi/10.1145/963770.963776) 293 | * 2008 294 | * [Collaborative Filtering for Implicit Feedback Datasets `AT&T`](http://yifanhu.net/PUB/cf.pdf) 295 | * 2009 296 | * [BPR: Bayesian Personalized Ranking from Implicit Feedback](https://arxiv.org/pdf/1205.2618.pdf) 297 | * [A Survey of Accuracy Evaluation Metrics of Recommendation Tasks `Evaluation` `Microsoft`](https://dl.acm.org/doi/10.5555/1577069.1755883) 298 | * 2010 299 | * [Collaborative filtering meets mobile recommendation: a user-centered approach `Microsoft`](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/AAAI10-Collaborative20Filtering20Meets20Mobile20Recommendation20A20User-centered20Approach-1.pdf) 300 | * [Factorization Machine (2010)](https://www.csie.ntu.edu.tw/~b97053/paper/Rendle2010FM.pdf) 301 | * 2011 302 | * [SLIM: Sparse Linear Methods for Top-N Recommender Systems (2011)](http://glaros.dtc.umn.edu/gkhome/fetch/papers/SLIM2011icdm.pdf) 303 | * [Adaptive bootstrapping of recommender systems using decision trees](https://dl.acm.org/doi/10.1145/1935826.1935910) 304 | * 2012 305 | * [A Topic-based Recommender System for Electronic Marketplace Platforms `Content-base`](https://ieeexplore.ieee.org/document/6495071) 306 | * 2013 307 | * [**Deep content-based music recommendation (2013 Spotify)**](https://papers.nips.cc/paper/2013/file/b3ba8f1bee1238a2f37603d90b58898d-Paper.pdf) 308 | * 2015 309 | * [A Probabilistic Model for Using Social Networks in Personalized Item Recommendation](https://dl.acm.org/doi/10.1145/2792838.2800193) 310 | * [AutoRec: Autoencoders Meet Collaborative Filtering (2015)`Autoencoder`](https://users.cecs.anu.edu.au/~akmenon/papers/autorec/autorec-paper.pdf) 311 | * [Metadata Embeddings for User and Item Cold-start Recommendations `Lyst` (LightFM)](https://arxiv.org/pdf/1507.08439.pdf) 312 | * -> [The Netflix Recommender System: Algorithms, Business Value and Innovation (2015 Netflix)](https://dl.acm.org/doi/pdf/10.1145/2843948) 313 | * 2016 314 | * [Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features `Microsoft`](https://dl.acm.org/doi/10.1145/2939672.2939704) 315 | * [Collaborative Denoising Auto-Encoders for Top-N Recommender Systems Dato `Autoencoder`](https://dl.acm.org/doi/pdf/10.1145/2835776.2835837) 316 | * [**Item2Vec: Neural Item Embedding for Collaborative Filtering `Microsoft`**](https://arxiv.org/abs/1603.04259) 317 | * [Session-based Recommendations with Recurrent Neural Networks `Yusp` `Telefonica` `Netflix` `Session-base`](https://arxiv.org/pdf/1511.06939.pdf) 318 | * [A Neural Autoregressive Approach to Collaborative Filtering `Autoencoder`](https://arxiv.org/abs/1605.09477) 319 | * [**Prod2vec: E-commerce in Your Inbox: Product Recommendations at Scale `Yahoo`**](https://arxiv.org/pdf/1606.07154.pdf) 320 | * [**Meta-Prod2Vec - Product Embeddings Using Side-Information for Recommendation `Criteo`**](https://arxiv.org/pdf/1607.07326.pdf) 321 | * [**Wide & Deep Learning for Recommender Systems `Google`**](https://arxiv.org/pdf/1606.07792.pdf) 322 | * [**Deep Neural Networks for YouTube Recommendations `Google`**](https://storage.googleapis.com/pub-tools-public-publication-data/pdf/45530.pdf) 323 | * [Recommendations as Treatments: Debiasing Learning and Evaluation](http://proceedings.mlr.press/v48/schnabel16.pdf) 324 | * -> [Local Item-Item Models For Top-N Recommendation](https://dl.acm.org/doi/pdf/10.1145/2959100.2959185) 325 | * [A Generic Coordinate Descent Framework for Learning from Implicit Feedback `Google`](https://arxiv.org/pdf/1611.04666.pdf) 326 | * [CB2CF: A Neural Multiview Content-to-Collaborative Filtering Model for Completely Cold Item Recommendations `Microsoft`](https://arxiv.org/abs/1611.00384) 327 | * 2017 328 | * [Diversity, Serendipity, Novelty, and Coverage: A Survey and Empirical Analysis of Beyond-Accuracy Objectives in Recommender Systems `Evaluation`](https://dl.acm.org/doi/10.1145/2926720) 329 | * [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://arxiv.org/abs/1701.04783) 330 | * [Sequential User-based Recurrent Neural Network Recommendations (2017)](https://dl.acm.org/doi/pdf/10.1145/3109859.3109877) 331 | * [Neural Collaborative Filtering (2017)](https://arxiv.org/pdf/1708.05031.pdf) 332 | * [Deep & Cross Network for Ad Click Predictions (2017 Google)](https://arxiv.org/pdf/1708.05123.pdf) 333 | * [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction (2017 Huawei)](https://arxiv.org/pdf/1703.04247.pdf) 334 | * [Deep & Cross Network for Ad Click Predictions V1 (2017 Google)](https://arxiv.org/pdf/1708.05123.pdf) 335 | * [Embedding-based News Recommendation for Millions of Users (Yahoo 2017)](http://library.usc.edu.ph/ACM/KKD%202017/pdfs/p1933.pdf) 336 | * [Folding: Why Good Models Sometimes Make Spurious Recommendations (2017 Google)](https://dl.acm.org/doi/pdf/10.1145/3109859.3109911) 337 | * [Collaborative Variational Autoencoder for Recommender Systems (2017)`Autoencoder`](https://eelxpeng.github.io/assets/paper/Collaborative_Variational_Autoencoder.pdf) 338 | * [Recurrent Neural Networks with Top-k Gains for Session-based Recommendations (2017 Yusp-Telefonica)](https://arxiv.org/pdf/1706.03847.pdf) 339 | * [Related Pins at Pinterest: The Evolution of a Real-World Recommender System `Pinterest`](https://arxiv.org/abs/1702.07969) 340 | * [ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation `Alibaba`](https://arxiv.org/abs/1711.06632) 341 | * [Large-Scale User Modeling with Recurrent Neural Networks for Music Discovery on Multiple Time Scales](https://arxiv.org/abs/1708.06520) 342 | * [Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks](https://arxiv.org/abs/1708.04617) 343 | * [Deep Embedding Forest: Forest-based Serving with Deep Embedding Features `Microsoft`](https://arxiv.org/abs/1703.05291) 344 | * [Collaborative Metric Learning `Evaluation`](https://dl.acm.org/doi/10.1145/3038912.3052639) 345 | * 2018 346 | * [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems (2018 Microsoft)](https://arxiv.org/pdf/1803.05170.pdf) 347 | * [Latent Cross: Making Use of Context in Recurrent Recommender Systems (2018 Google)](https://dl.acm.org/doi/pdf/10.1145/3159652.3159727) 348 | * [Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts (2018 Google)](https://dl.acm.org/doi/pdf/10.1145/3219819.3220007) 349 | * [Practical Diversified Recommendations on YouTube with Determinantal Point Processes (2018 Google)](https://dl.acm.org/doi/pdf/10.1145/3269206.3272018) 350 | * [Explore, exploit, and explain: personalizing explainable recommendations with bandits (2018 Spotify)](https://dl.acm.org/doi/pdf/10.1145/3240323.3240354) 351 | * [MULTI-VAE: Variational Autoencoders for Collaborative Filtering (2018 Netflix/Google)`Autoencoder`](https://arxiv.org/pdf/1802.05814.pdf) 352 | * [Practical Diversified Recommendations on YouTube with Determinantal Point Processes (2018 Google)](https://dl.acm.org/doi/pdf/10.1145/3269206.3272018) 353 | * [Adversarial Collaborative Auto-encoder for Top-N Recommendation (2018)](https://arxiv.org/pdf/1808.05361.pdf) 354 | * [Causal Embeddings for Recommendation]() 355 | * [Sequence-Aware Recommender Systems](https://arxiv.org/abs/1802.08452) 356 | * [Offline A/B testing for Recommender Systems `Criteo`](https://arxiv.org/abs/1801.07030) 357 | * [**Deep neural network marketplace recommenders in online experiments `Schibsted`**](https://arxiv.org/abs/1809.02130) / [**Five lessons from building a deep neural network recommender**](https://arxiv.org/abs/1809.02131) 358 | * [Learning Item-Interaction Embeddings for User Recommendations `Etsy`](https://arxiv.org/abs/1812.04407) 359 | * [Word2Vec applied to Recommendation: Hyperparameters Matter `Deezer`](https://arxiv.org/abs/1804.04212) 360 | * [Calibrated recommendations `Evaluation` `Netflix`](https://dl.acm.org/doi/10.1145/3240323.3240372) 361 | 362 | * 2019 363 | * [Deep Learning Recommendation Model for Personalization and Recommendation Systems (2019 Facebook)](https://arxiv.org/pdf/1906.00091.pdf) 364 | * [**Sampling-bias-corrected neural modeling for large corpus item recommendations (2019 Google)`Two tower`**](https://storage.googleapis.com/pub-tools-public-publication-data/pdf/6c8a86c981a62b0126a11896b7f6ae0dae4c3566.pdf) 365 | - [**PS6: Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations - Yi et al. (ACM)**](https://www.youtube.com/watch?v=O4cqDdtflnY) 366 | - [PR-282: Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations](https://www.youtube.com/watch?v=FSDuo9ybv8s) 367 | * [Recommending what video to watch next: a multitask ranking system (2019 Google)](https://dl.acm.org/doi/pdf/10.1145/3298689.3346997) 368 | * [SNR: Sub-Network Routing for Flexible Parameter Sharing in Multi-Task Learning (2019 Google)](https://ojs.aaai.org/index.php/AAAI/article/view/3788) 369 | * [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer (2019)](https://dl.acm.org/doi/abs/10.1145/3357384.3357895) 370 | * [Improving Relevance Prediction with Transfer Learning in Large-scale Retrieval Systems (2019 Google)](https://openreview.net/pdf?id=SJxPVcSonN) 371 | * [Building a Recommender System Using Embeddings (2019 Drop)](https://drop.engineering/building-a-recommender-system-using-embeddings-de5a30e655aa) 372 | * [End-to-End Retrieval in Continuous Space (2019 Google) `Two tower`](https://arxiv.org/pdf/1811.08008.pdf) 373 | * [Beyond Greedy Ranking: Slate Optimization via List-CVAE (2019)`Autoencoder`](https://arxiv.org/pdf/1803.01682.pdf) 374 | * [On the Difficulty of Evaluating Baselines (2019 Google)`evaluation`](https://arxiv.org/pdf/1905.01395.pdf) 375 | * [**Are we really making much progress? A worrying analysis of recent neural recommendation approaches** (2019)`evaluation`](https://dl.acm.org/doi/pdf/10.1145/3298689.3347058) 376 | * [**Embarrassingly Shallow Autoencoders for Sparse Data** (2019 Netflix)`autoencoder`](https://arxiv.org/abs/1905.03375) 377 | * [Collaborative Filtering via High-Dimensional Regression (2019 Netflix)](https://arxiv.org/pdf/1904.13033.pdf) 378 | * [RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback (2019 Samsung)](https://arxiv.org/pdf/1912.11160.pdf) 379 | * [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba (2019 Alibaba)](https://arxiv.org/pdf/1905.06874.pdf) 380 | * [**Managing Popularity Bias in Recommender Systems with Personalized Re-ranking** (2019)](https://arxiv.org/pdf/1901.07555.pdf) 381 | * [KGAT: Knowledge Graph Attention Network for Recommendation](https://arxiv.org/abs/1905.07854) 382 | * [AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://arxiv.org/abs/1810.11921) 383 | * [Recommending what video to watch next: a multitask ranking system `Google`](https://daiwk.github.io/assets/youtube-multitask.pdf) 384 | * [PAL: a position-bias aware learning framework for CTR prediction in live recommender systems `Huawei`](https://www.researchgate.net/publication/335771749_PAL_a_position-bias_aware_learning_framework_for_CTR_prediction_in_live_recommender_systems) 385 | * 2020 386 | * [SSE-PT: Sequential Recommendation Via Personalized Transformer](https://dl.acm.org/doi/10.1145/3383313.3412258) 387 | * [DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems (2020 Google)](https://arxiv.org/pdf/2008.13535.pdf) 388 | * [Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations (2020 Tencet)](https://dl.acm.org/doi/pdf/10.1145/3383313.3412236) 389 | * [Contextual and Sequential User Embeddings for Large-Scale Music Recommendation (2020)](https://dl.acm.org/doi/pdf/10.1145/3383313.3412248) 390 | * -> [P-Companion: A Principled Framework for Diversified Complementary Product Recommendation (2020 Aamzon)](https://dl.acm.org/doi/pdf/10.1145/3340531.3412732) 391 | * [Improving complementary-product recommendations `Amazon`](https://www.amazon.science/blog/improving-complementary-product-recommendations) 392 | * [Pre-training Tasks for Embedding-based Large-scale Retrieval (2020 Google)](https://arxiv.org/pdf/2002.03932.pdf) 393 | * [Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations (2020 Google)`two tower`](https://storage.googleapis.com/pub-tools-public-publication-data/pdf/b9f4e78a8830fe5afcf2f0452862fb3c0d6584ea.pdf) 394 | * [On sampled metrics for item recommendation (2020 Google)](https://dl.acm.org/doi/pdf/10.1145/3394486.3403226) 395 | * [Temporal-Contextual Recommendation in Real-Time (2020 Amazon)](https://dl.acm.org/doi/pdf/10.1145/3394486.3403278) 396 | * [**Neural Collaborative Filtering vs. Matrix Factorization Revisited `Google`**](https://dl.acm.org/doi/pdf/10.1145/3383313.3412488) 397 | * [An Embedding Learning Framework for Numerical Features in CTR Prediction](https://arxiv.org/pdf/2012.08986.pdf) 398 | * [Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations (ByteDance)](https://arxiv.org/pdf/2007.07203v2.pdf) 399 | * [Embedding-based Retrieval in Facebook Search `Facebook` `Two tower`](https://dl.acm.org/doi/pdf/10.1145/3394486.3403305) 400 | * -> [Causal Inference for Recommender Systems](https://dl.acm.org/doi/10.1145/3383313.3412225) 401 | * [Off-policy Learning in Two-stage Recommender Systems `Two tower`](https://dl.acm.org/doi/abs/10.1145/3366423.3380130) 402 | * [How to Grow a (Product) Tree: Personalized Category Suggestions for eCommerce Type-Ahead `Coveo`](https://aclanthology.org/2020.ecnlp-1.2/) 403 | * [Fantastic Embeddings and How to Align Them: Zero-Shot Inference in a Multi-Shop Scenario `Coveo`](https://arxiv.org/abs/2007.14906) 404 | * [RecoBERT: A Catalog Language Model for Text-Based Recommendations `Micorsoft`](https://arxiv.org/abs/2009.13292) 405 | * [Attentive Item2Vec: Neural Attentive User Representations `Microsoft`](https://arxiv.org/abs/2002.06205) 406 | * [Neural Interactive Collaborative Filtering](https://arxiv.org/abs/2007.02095) 407 | 408 | 409 | * 2021 410 | * [Exploring Heterogeneous Metadata for Video Recommendation with Two-tower Model (2021 Amazon)](https://arxiv.org/pdf/2109.11059.pdf) 411 | * [Theoretical Understandings of Product Embedding for E-commerce Machine Learning (2021 Walmart)](https://arxiv.org/pdf/2102.12029.pdf) 412 | * [**Self-supervised Learning for Large-scale Item Recommendations (2021 Google)** `two tower`](https://arxiv.org/pdf/2007.12865.pdf ) 413 | * [Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees? (2021 Google ICRL)](https://storage.googleapis.com/pub-tools-public-publication-data/pdf/a7f0822e77e8b6b4c00c879707fe60e3955d4a03.pdf) 414 | * [**Item Recommendation from Implicit Feedback (2021 Google)**](https://arxiv.org/pdf/2101.08769.pdf) 415 | * [A Troubling Analysis of Reproducibility and Progress in Recommender Systems Research (2021)`review`](https://arxiv.org/pdf/1911.07698.pdf) 416 | * [One Person, One Model, One World: Learning Continual User Representation without Forgetting (2021)](https://arxiv.org/pdf/2009.13724.pdf) 417 | * [Towards Source-Aligned Variational Models for Cross-Domain Recommendation `autoencoder`](https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7433&context=sis_research ) 418 | * [**Negative Interactions for Improved Collaborative Filtering: Don’t go Deeper, go Higher (Netflix)**](https://dl.acm.org/doi/pdf/10.1145/3460231.3474273) 419 | * -> [Shared Neural Item Representations for Completely Cold Start Problem ()](https://dl.acm.org/doi/abs/10.1145/3460231.3474228) 420 | * [Reenvisioning the comparison between Neural Collaborative Filtering and Matrix Factorization](https://dl.acm.org/doi/abs/10.1145/3460231.3475944) 421 | * [**Graph Learning based Recommender Systems: A Review**`review`](https://arxiv.org/pdf/2105.06339.pdf) 422 | * [Reinforcement learning based recommender systems: A survey`survey`](https://arxiv.org/pdf/2101.06286.pdf) 423 | * [**Recommendations as Treatments**](https://ojs.aaai.org/index.php/aimagazine/article/view/18141/18875) 424 | * [**Deep Learning for Recommender Systems: A Netflix Case Study** `Netflix`](https://ojs.aaai.org/index.php/aimagazine/article/view/18140/18876) 425 | * [Query2Prod2Vec: Grounded Word Embeddings for eCommerce `Coveo`](https://aclanthology.org/2021.naacl-industry.20/) 426 | * [A/B Testing for Recommender Systems in a Two-sided Marketplace `Linedin`](https://arxiv.org/abs/2106.00762) 427 | * [A Constrained Optimization Approach for Calibrated Recommendations `Evaluation`](https://dl.acm.org/doi/fullHtml/10.1145/3460231.3478857) 428 | * 2022 429 | * [Cross Pairwise Ranking for Unbiased Item Recommendation](https://arxiv.org/pdf/2204.12176v1.pdf) 430 | * [Towards Universal Sequence Representation Learning for Recommender Systems](https://arxiv.org/abs/2206.05941)[Code](https://github.com/rucaibox/unisrec) 431 | * [Weighing dynamic availability and consumption for Twitch recommendations (Amazon)](https://www.amazon.science/publications/weighing-dynamic-availability-and-consumption-for-twitch-recommendations) 432 | * [ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest](https://arxiv.org/pdf/2205.11728.pdf) 433 | * [**A Brief History of Recommender Systems `Review`**](https://arxiv.org/abs/2209.01860) 434 | * 2023 435 | * [Calibrated Recommendations as a Minimum-Cost Flow Problem `Evaluation` `Spotify`](https://dl.acm.org/doi/10.1145/3539597.3570402) 436 | 437 | 438 | ### Papers by topics 439 | 440 | tower model 441 | * [Learning Text Similarity with Siamese Recurrent Networks (2016 textkernel)](https://aclanthology.org/W16-1617.pdf) 442 | * [Smart Reply: Automated Response Suggestion for Email (2016 Google)](https://arxiv.org/pdf/1606.04870v1.pdf) 443 | * [Learning Semantic Textual Similarity from Conversations - (2018 Google)](https://arxiv.org/pdf/1804.07754.pdf) 444 | 445 | Product search recommendation 446 | * [A Transformer-based Embedding Model for Personalized Product Search (2020)](https://arxiv.org/pdf/2005.08936.pdf) 447 | 448 | eCommerce 449 | * [Predicting Shopping Behavior with Mixture of RNNs (2017 Rakuten)](https://difabbrizio.com/papers/sigir-ecom-2017-cs.pdf) 450 | * [Fantastic Embeddings and How to Align Them: Zero-Shot Inference in a Multi-Shop Scenario (2020 Coveo)](https://arxiv.org/pdf/2007.14906.pdf) 451 | * [Shopping in the Multiverse: A Counterfactual Approach to In-Session Attribution (2020 Coveo)](https://arxiv.org/pdf/2007.10087.pdf) 452 | * [How to Grow a (Product) Tree Personalized Category Suggestions for eCommerce Type-Ahead (2020 Coveo)](https://aclanthology.org/2020.ecnlp-1.2.pdf) 453 | * [Shopper intent prediction from clickstream e‑commerce data with minimal browsing information (2020)](https://www.nature.com/articles/s41598-020-73622-y.pdf) 454 | 455 | 456 | ## Recsys Conference 457 | * [ACM Recsys](https://recsys.acm.org/) 458 | * [ACM Recsys conference](https://dl.acm.org/conference/recsys) 459 | * [ACM SIGIR Conference on Research and Development in Information Retrieval](https://sigir.org/sigir2022/) 460 | * [ACM International Conference on Information and Knowledge Management - CIKM](https://www.cikm2021.org/) 461 | 462 | ### Videos 463 | RecSys 2020 (https://slideslive.com/acmrecsys) 464 | * [**A Human Perspective on Algorithmic Similarity** `Netflix`](https://slideslive.com/38934788) 465 | * [**Balancing Relevance and Discovery to Inspire Customers in the IKEA App** `IKEA`](https://slideslive.com/38934789) 466 | * [**Behavior-based Popularity Ranking on Amazon Video** `Amazon`](https://slideslive.com/38934790) 467 | * [**Building a Reciprocal Recommendation System at Scale From Scratch: Learnings from One of Japan's Prominent Dating Applications** `Tapple`](https://slideslive.com/38934791) 468 | * [Counterfactual Learning for Recommender System `Huawei`](https://slideslive.com/38934792) 469 | * [Developing Recommendation System to provide a Personalized Learning experience at Chegg `Chegg`](https://slideslive.com/38934793) 470 | * [Investigating Multimodal Features for Video Recommendations at Globoplay `Globoplay`](https://slideslive.com/38934794) 471 | * [On the Heterogeneous Information Needs in the Job Domain: A Unified Platform for Student Career `Talto`](https://slideslive.com/38934795) 472 | * [Query as Context for Item-to-Item Recommendation `Etsy`](https://slideslive.com/38934796) 473 | * [The Embeddings that Came in From the Cold: Improving Vectors for New and Rare Products with Content-Based Inference `Coveo`](https://slideslive.com/38934797) 474 | 475 | 476 | 477 | 478 | ## Other Awesone list 479 | * https://github.com/hongleizhang/RSPapers 480 | * https://github.com/wzhe06/Reco-papers 481 | * https://github.com/robi56/Deep-Learning-for-Recommendation-Systems 482 | * https://paperswithcode.com/task/recommendation-systems?page=2 483 | * https://github.com/microsoft/recommenders 484 | * https://github.com/guyulongcs/Awesome-Deep-Learning-Papers-for-Search-Recommendation-Advertising 485 | * https://github.com/scnu-dil/awesome-RecSys 486 | * [SIGIR (Special Interest Group on Information Retrieval)](https://sigir-ecom.github.io/) 487 | * [Papers with code](https://paperswithcode.com/task/recommendation-systems) 488 | 489 | # Profesors 490 | * [Thorsten Joachims, Cornell University](https://www.cs.cornell.edu/people/tj/) 491 | --------------------------------------------------------------------------------